MIL includes a Classification tool for automatically categorizing image content using machine learning. It makes use of deep learning—specifically convolutional neural network (CNN)—technology for assigning images or image regions to pre-established classes. The tool is particularly well-suited for analyzing images of highly textured, naturally varying, and acceptably deformed goods. The intricate design and training of a neural network is carried out by Matrox Imaging, taking advantage of the accumulated experience, knowledge, and skill of its experts in both machine learning and machine vision. Users simply need to submit an adequate set of images that are representative of the given application, categorized for the desired classes, and roughly distributed evenly among the latter. The prediction or inference with the neural network is then performed exclusively by Matrox Imaging-written code on a mainstream CPU, eliminating the dependence on third-party neural network libraries and the need for specialized GPU hardware.

Click to enlarge


3. Through an update.

More tools >